The use of artificial intelligence (AI) has the potential to improve the assessment of lesions suspicious of melanoma, but few clinical studies have been conducted. We validated the accuracy of an open-source, non-commercial AI algorithm for melanoma diagnosis and assessed its potential impact on dermatologist decision-making. We conducted a prospective, observational clinical study to assess the diagnostic accuracy of the AI algorithm (ADAE) in predicting melanoma from dermoscopy skin lesion images. The primary aim was to assess the reliability of ADAE’s sensitivity at a predefined threshold of 95%. Patients who had consented for a skin biopsy to exclude melanoma were eligible. Dermatologists also estimated the probability of melanoma and indicated management choices before and after real-time exposure to ADAE scores. All lesions underwent biopsy. Four hundred thirty-five participants were enrolled and contributed 603 lesions (95 melanomas). Participants had a mean age of 59 years, 54% were female, and 96% were White individuals. At the predetermined 95% sensitivity threshold, ADAE had a sensitivity of 96.8% (95% CI: 91.1–98.9%) and specificity of 37.4% (95% CI: 33.3–41.7%). The dermatologists’ ability to assess melanoma risk significantly improved after ADAE exposure (AUC 0.7798 vs. 0.8161, p = 0.042). Post-ADAE dermatologist decisions also had equivalent or higher net benefit compared to biopsying all lesions. We validated the accuracy of an open-source melanoma AI algorithm and showed its theoretical potential for improving dermatology experts’ ability to evaluate lesions suspicious of melanoma. Larger randomized trials are needed to fully evaluate the potential of adopting this AI algorithm into clinical workflows.

No abstract

BackgroundRecruiting a hidden population, such as the population of women at risk for alcohol-exposed pregnancy (AEP) who binge drink and are at risk of an unintended pregnancy, is challenging as this population is not typically seeking help or part of an identifiable group. We sought to identify affordable and efficient methods of recruitment for hidden populations.MethodsSeveral popular online social media and advertising sites were identified. Cities with high rates of binge drinking among women were targeted. We placed advertisements and study notices using Facebook, Twitter, Craigslist, University postings, and ClinicalTrials.gov.ResultsFor this study, 75 women at risk for AEP were recruited from across the U.S. within 7 months. Online advertising for study participants on Craigslist resulted in enrollment of the majority 51 (68%) of the study participants. While Craigslist advertising could be tailored to specific locations with high rates of binge drinking among women, there were challenges to using Craigslist. These included automated deletion due to repeated postings and mention of sexual behavior or drinking, requiring increased efforts and resources by the study team. Several strategies were developed to optimize advertising on Craigslist. Approximately 100 h of staff time valued at $2500 was needed over the 7-month recruitment period.DiscussionDespite challenges, the target sample of women at risk for AEP was recruited in the 7 month recruitment period using online advertising methods. We recommend that researchers consider online classified advertisements when recruiting from non-help seeking populations. By taking advantage of national data to target specific risk factors, and by tailoring advertising efforts, it is possible to efficiently and affordably recruit a non-treatment seeking sample.

No abstract